< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 68 in Layer 29

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.5106. Min Act: -0.1700

Data Index: 7044347 (Open Web Text)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.4794. Min Act: -0.1700

Data Index: 450832 (Open Web Text)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.2606. Min Act: -0.1700

Data Index: 5201239 (Open Web Text)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.2606. Min Act: -0.1700

Data Index: 217870 (Open Web Text)

Max Activating Token Index: 245

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.2606. Min Act: -0.1700

Data Index: 908957 (Open Web Text)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.2294. Min Act: -0.1700

Data Index: 8011332 (Open Web Text)

Max Activating Token Index: 551

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.1981. Min Act: -0.1700

Data Index: 8529058 (Open Web Text)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.1669. Min Act: -0.1700

Data Index: 1188001 (Open Web Text)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.1356. Min Act: -0.1700

Data Index: 5264702 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.1356. Min Act: -0.1700

Data Index: 4625293 (Open Web Text)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.1356. Min Act: -0.1700

Data Index: 2360851 (Open Web Text)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.1356. Min Act: -0.1700

Data Index: 3899970 (Open Web Text)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.0731. Min Act: -0.1700

Data Index: 3355252 (Open Web Text)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.1044. Min Act: -0.1700

Data Index: 5058151 (Open Web Text)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.0731. Min Act: -0.1700

Data Index: 3906777 (Open Web Text)

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.0731. Min Act: -0.1700

Data Index: 6373359 (Open Web Text)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.0419. Min Act: -0.1700

Data Index: 2741294 (Open Web Text)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.0419. Min Act: -0.1700

Data Index: 8615020 (Open Web Text)

Max Activating Token Index: 199

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.0106. Min Act: -0.1700

Data Index: 3037888 (Open Web Text)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.5106. Min Range: -5.5106

Max Act: 5.0106. Min Act: -0.1700

Data Index: 7641677 (Open Web Text)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #19